{"id":"W4416677163","doi":"10.1109/iccams65118.2025.11234065","title":"Analyzing Data from Social Media to Make Predictions Regarding the Behaviour Patterns of Customers","year":2025,"lang":"","type":"article","venue":"","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lockheed Martin (Canada)","funders":"","keywords":"Hyperparameter; Social media; Bayesian probability; Bayesian optimization; Artificial neural network; Field (mathematics); Bayesian network; Tree (set theory); Predictive modelling","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007329265,0.001126298,0.0005883645,0.002912928,0.000271241,0.0008963486,0.0006088428,0.0007265931,0.00199187],"category_scores_gemma":[0.003791079,0.0002618875,0.0007268819,0.002647506,0.0002479023,0.001834064,0.0005986719,0.0009392654,0.001559276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004462114,"about_ca_system_score_gemma":0.0004019806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006481327,"about_ca_topic_score_gemma":0.009293183,"domain_scores_codex":[0.9994494,0.0001107855,0.00004408849,0.0001207098,0.0002133027,0.00006167813],"domain_scores_gemma":[0.9984706,0.0008585415,0.0001938325,0.0001445965,0.0002888677,0.0000435925],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0004520404,0.0009963176,0.1773024,0.001106286,0.000531635,0.0008466361,0.0008033778,0.1089583,0.01670857,0.006724179,0.0145571,0.6710132],"study_design_scores_gemma":[0.00000908056,0.000172924,0.04815552,0.0001499561,0.000110375,0.0002217542,0.0005678911,0.9262297,0.008275633,0.01100976,0.005044042,0.00005329246],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6002833,0.003355852,0.359927,0.002822186,0.0005093525,0.0004525151,0.01347773,0.0036959,0.01547605],"genre_scores_gemma":[0.9359764,0.00193091,0.05187774,0.0002523468,0.0002376917,0.0002136849,0.006271373,0.00008209066,0.003157908],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006481327,"threshold_uncertainty_score":0.01288718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04552349528985278,"score_gpt":0.2926395938243911,"score_spread":0.2471160985345383,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}